paper-with-me

Papers

FREYR: A Framework for Recognizing and Executing Your Requests

2025-01-21 · Roberto Gallotta, Antonios Liapis, Georgios N. Yannakakis

Large language models excel as conversational agents, but their capabilities can be further extended through tool usage, i.e.: executable code, to enhance response accuracy or address specialized domains. Current approaches to enable tool usage often rely on model-specific prompting or fine-tuning a model for function-calling instructions. Both approaches have notable limitations, including reduced adaptability to unseen tools and high resource requirements. This paper introduces FREYR, a streamlined framework that modularizes the tool usage process into separate steps. Through this decomposition, we show that FREYR achieves superior performance compared to conventional tool usage methods. We evaluate FREYR on a set of real-world test cases specific for video game design and compare it against traditional tool usage as provided by the Ollama API.

📄 PDF Abstract BibTeX arXiv:2501.12423

Code (1)

gallorob/freyr 공식 구현

Tasks

Game Design

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Improving the Accuracy of the CogniLearn System for Cognitive Behavior Assessment

2017-03-25 · Amir Ghaderi, Srujana Gattupalli, Dylan Ebert, Ali Sharifara 외

HTKS is a game-like cognitive assessment method, designed for children between four and eight years of age. During the HTKS assessment, a child responds to a sequence of requests, such as "touch your head" or "touch your…

Accelerating Serverless Computing by Harvesting Idle Resources

2021-08-28 · Hanfei Yu, Hao Wang, Jian Li, Xu Yuan 외

Serverless computing automates fine-grained resource scaling and simplifies the development and deployment of online services with stateless functions. However, it is still non-trivial for users to allocate appropriate r…

Deep Reinforcement Learning

Back up your Stance: Recognizing Arguments in Online Discussions

2014-06-01 · WS 2014 6 · Filip Boltu{\v{z}}i{\'c}, Jan {\v{S}}najder
Information RetrievalOpinion Mining

Optimizing LLM Inference for Database Systems: Cost-Aware Scheduling for Concurrent Requests

2024-11-12 · Kyoungmin Kim, Kijae Hong, Caglar Gulcehre, Anastasia Ailamaki

LLMs are increasingly used inside database systems and in database applications for better complexity management and decision-making, where LLM inferences require significant GPU costs. LLM inference systems, however, ar…

Decision MakingGPUManagementScheduling

PACE: Towards Surfacing Hidden Conflicts in User Requests

2026-09-03 · Yoojin Kim, Jihyoung Jang, Hyounghun Kim hf

Personalized assistants should not only comply with user requests but also assess whether those requests are appropriate given the user's current circumstances. However, prior work has primarily focused on accurately exe…